Hotel Lobby AI with your best friend
Two separate portraits, shot against two different walls, come back side by side in one booth. Faces, hair, sweatshirt and overshirt carry over from the photos.
Upload two photos and get the Hotel Lobby AI trend clip: the pair of you in the orange booth, trading bars at one hanging mic. Vertical 9:16, 4 seconds, and your first video is free after you follow us.
Follow us and get 20 free credits — about 1 video
For photos of yourself or people who agreed to appear.
Real output from this page: two portraits in, one booth out.
Subscribe for more credits and more models.
Real output from this page at the tier the free credits cover — the photos that went in on the left, the clip that came out on the right.
Two separate portraits, shot against two different walls, come back side by side in one booth. Faces, hair, sweatshirt and overshirt carry over from the photos.
The mic hangs between you and you take turns on it. Neither of you needs to be a rapper: the model supplies the gestures and the head bobs.
Already have a picture of the two of you? Upload just that. One shared photo keeps both faces closest to real, because the model sees you together.
Cats were one of the first versions of this trend to go viral, and they still work best. Upload one photo per pet; paws and open mouths do the rapping.
What the account behind this page gets you, beyond one trend clip.
No subscription to start. Following us earns 20 credits, and a clip here spends 20.
The same balance runs every tool and every model on the account.
Switch the tier above the button: up to 15 seconds, and 1080p on Seedance 2.5.
Seedance, Kling 3.0 Omni and more on one account, as soon as they ship.
Upload two photos — or one photo with both of you in it — and the Hotel Lobby AI video generator returns a 4-second vertical clip of the two of you in an orange studio booth, trading bars at one microphone hanging from the ceiling. It takes about two minutes and there is nothing to write or set.
The clip is silent. Add the Hotel Lobby sound from the music library when you post it on TikTok or Instagram, and the trend is complete.
Want the whole story of the trend and every way to make it? Read the Migos AI video guide
Two photos, one button. The clip is always vertical, so it is ready for TikTok and Reels as it comes.
One front-facing photo per person or pet, waist-up or full body. Or one photo with both of you in it.
480p, 4 seconds and 9:16 are preselected — what the free credits cover. The line above the button reprices other tiers.
Download the MP4, upload it to TikTok or Reels, and pick the Hotel Lobby sound from the app’s music library.
There are two ways to make this clip: generate a new performance from photos, or copy the moves of an existing clip onto new people. Higgsfield figures are from higgsfield.ai/blog/higgsfield-genjutsu, accessed 29 September 2026; ours are measured on this page.
| What you get | This page (Recommended) | Higgsfield Genjutsu Motion Transfer | Renoise face swap video |
|---|---|---|---|
| What you upload | Two photos, or one of you both | A 4–30s source clip + up to 30 images | Your own clip (≤15s) + one face |
| Copies the original moves | — | ✓ | ✓ of your clip |
| Needs the original clip | — | ✓ | ✓ |
| Default output | 480p · 4s · 9:16 | Up to 1080p, source length | Source length |
| Entry cost | 20 credits a clip | 40 credits for 15s at 480p | 6 credits a second |
| First one free | ✓ | — | — |
This page generates a new clip in the look of the trend: two people, an orange booth, one microphone hanging on a cable, a static front camera. It does not take the original performance and paste your faces onto it. The moves are the model’s, not a frame-by-frame copy of the 2022 session, and no footage, likeness or audio from that session is used. That is also why it needs nothing from you but photos. If you want the original choreography, that is motion transfer — you supply the clip, and Higgsfield Genjutsu or our face swap video tool maps new faces onto its moves.
Four seconds is one exchange: one of you raps, the other answers or hypes. It is enough for a loop on TikTok, and it is not the whole verse. For a longer take, the line above the button runs up to 15 seconds, and Seedance 2.5 renders it at 1080p; it shows the price before you commit. The free clip is watermarked and silent — the sound comes from the app you post it on.
Use photos of yourself, or of people who agreed to be in the clip. Putting a stranger or a celebrity in the booth is still synthetic media about a real person, and never use photos of minors.
What happens to an upload on this page.
Picking a file only previews it on your device. Not one byte is stored until you sign in and click generate.
Uploads land in your private library, never a public gallery, and re-running the same photo stores nothing new.
Remove uploads and results from your library whenever you want.
One plan unlocks Seedance, Kling 3.0 Omni and every other video model.
For first-time AI content creators
Billed $168 annually
Upgrade PlanSave $72/year
For creators shipping content every week.
Billed $504 annually
Upgrade PlanSave $216/year
For studios and pros producing at commercial scale.
Billed $1680 annually
Upgrade PlanSave $720/year
For first-time AI content creators
Billed monthly
Upgrade PlanFor creators shipping content every week.
Billed monthly
Upgrade PlanFor studios and pros producing at commercial scale.
Billed monthly
Upgrade PlanRenews automatically each year until canceled.
Renews automatically each month until canceled.
Your first clip is free. Following us on X and YouTube earns 20 credits and one clip at the default 480p, 4-second tier costs 20 at list price. After that each clip is billed per generation — there is no free plan and no trial period.
A TikTok trend from September 2026 that puts two people into the orange booth of a 2022 COLORS performance of the song "Hotel Lobby", sharing one hanging microphone. Creators upload two photos to an AI video tool and post the result with the song.
Not as a one-tap camera filter. Every version you see is an AI video made from photos and then posted with the sound. This page is that step: two photos in, a vertical clip out, ready to post.
Either works. One photo of the two of you keeps both faces closest to real, because the model sees you together. Two separate portraits also work — the model then places you side by side and the likeness can drift slightly.
The clip is generated silent so the free tier stays cheap and reliable. Add the Hotel Lobby sound from TikTok or Instagram’s music library when you post — that keeps the track licensed and in sync with the trend.
Yes. 480p and 4 seconds is only the default because that is what the free credits cover. The line above the button goes to 720p on Seedance 2.0 Mini, 1080p on Seedance 2.5, and up to 15 seconds either way, priced before you run it.
Yes — pets were among the first versions of the trend to go viral. Upload one clear photo of each pet, sitting upright and facing the camera. The same works for dogs, or a pet and a person.
No. Higgsfield Genjutsu copies the moves of a source clip onto your photos, which needs that clip. This page generates the scene from your photos alone, so there is nothing else to find or upload.
No. Failed and cancelled generations refund their credits automatically. The usual causes are a face the model cannot read — small, turned away or shadowed — or the content filter declining the photo itself.
Two photos, four seconds, your first clip free.


